Esophageal Tumor Segmentation in CT Images Using a Dilated Dense Attention Unet (DDAUnet)
Open Access
- 12 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 99235-99248
- https://doi.org/10.1109/access.2021.3096270
Abstract
Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim to investigate if and to what extent a simplified clinical workflow based on CT alone, allows one to automatically segment the esophageal tumor with sufficient quality. For this purpose, we present a fully automatic end-to-end esophageal tumor segmentation method based on convolutional neural networks (CNNs). The proposed network, called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channel attention gates in each dense block to selectively concentrate on determinant feature maps and regions. Dilated convolutional layers are used to manage GPU memory and increase the network receptive field. We collected a dataset of 792 scans from 288 distinct patients including varying anatomies with air pockets, feeding tubes and proximal tumors. Repeatability and reproducibility studies were conducted for three distinct splits of training and validation sets. The proposed network achieved a DSC value of 0.79 ± 0.20, a mean surface distance of 5.4 ± 20.2mm and 95% Hausdorff distance of 14.7 ± 25.0mm for 287 test scans, demonstrating promising results with a simplified clinical workflow based on CT alone. Our code is publicly available via https://github.com/yousefis/DenseUnet_Esophagus_Segmentation .This publication has 33 references indexed in Scilit:
- Quantification of Esophageal Tumor Motion on Cine-Magnetic Resonance ImagingInternational Journal of Radiation Oncology*Biology*Physics, 2014
- Model-Based Esophagus Segmentation from CT Scans Using a Spatial Probability MapLecture Notes in Computer Science, 2010
- Fast Automatic Segmentation of the Esophagus from 3D CT Data Using a Probabilistic ModelLecture Notes in Computer Science, 2009
- Automatic Detection of Air Holes Inside the Esophagus in CT ImagesInformatik aktuell, 2008
- Esophagus Segmentation by Spatially-Constrained Shape InterpolationInformatik aktuell, 2008
- FDG-PET/CT Tumor Segmentation-Derived Indices of Metabolic Activity to Assess Response to Neoadjuvant Therapy and Progression-Free Survival in Esophageal CancerAmerican Journal of Clinical Oncology, 2007
- Semi-automated CT segmentation using optic flow and Fourier interpolation techniquesComputer Methods and Programs in Biomedicine, 2006
- Esophageal CancerThe New England Journal of Medicine, 2003
- Monte Carlo cross validationChemometrics and Intelligent Laboratory Systems, 2001
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997